Artificial intelligence-enabled coconut tree disease detection and classification model for smart agriculture. (December 2022)

• Record Type: Journal Article
• Authors: Maray, Mohammed; Albraikan, Amani Abdulrahman; Alotaibi, Saud S.; Alabdan, Rana; Duhayyim, Mesfer Al; Al-Azzawi, Waleed Khaild; alkhayyat, Ahmed
• Is Part Of: Computers & electrical engineering. Volume 104:Part A(2022)
• Publication Date: 2022-12
• Subjects: Smart agriculture -- Deep learning -- Coconut tree detection -- Image processing -- Computer vision -- Hyperparameter optimization -- Crop productivity; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108399
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Develop an AI enabled Coconut Tree Disease Detection model. Present AIE-CTDDC model with Bayesian fuzzy clustering-based segmentation. Apply Harris Hawks Optimizer with gated recurrent unit for classification. Achieves higher accuracy of 97.75% on coconut tree disease classification. Abstract: Real-time and accurate plant disease recognition systems help in the development of disease mitigation strategies and ensure food security on a large scale compounded with small-scale economic crop protection. The current research article presents an Artificial Intelligence Enabled Coconut Tree Disease Detection and Classification (AIE-CTDDC) model for smart agriculture. The aim of the presented AIE-CTDDC technique is to classify the coconut tree diseases in a smart farming environment so as to enhance the crop productivity. Firstly, the AIE-CTDDC model applies median filtering-based noise removal technique. Then, the Bayesian fuzzy clustering-based segmentation method is employed for the detection of the affected leaf regions. Besides, the capsule network (CapsNet) method is exploited as a feature extractor. In this study, the Harris Hawks Optimization (HHO) with Gated Recurrent Unit (GRU) model is exploited for the detection of diseases in coconut trees. The experimental analysis was conducted upon AIE-CTDDC model and the outcomes confirmed the better performance of the proposed AIE-CTDDC model over recent state-of-the-art techniques. Graphical abstract: Image, graphical abstract